memory_forget

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden; it does add real behavioral value by disclosing that deletes are soft by default with audit records retained, and that hard=true is a physical deletion. It omits permissions/authorization, whether hard delete is reversible, and critically what happens when neither ids nor query is supplied given zero required parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence, front-loaded with the verb and the two selection modes, with the destructive-flag detail placed last where it matters. Nothing redundant, though the density means the parameter interaction stays unexplained.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive 4-parameter tool with zero required params, a nested scope object, no annotations and no output schema, the description covers the safety-critical soft/hard distinction but leaves open the risk of an unscoped mass delete, permission requirements, and return/confirmation behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 25%, with only the nested scope object documented. The description rescues the meaning of `hard` (default false, physical vs audit-preserving) and loosely maps ids/query as the two selection paths, but says nothing about how ids and query interact, how scope narrows the deletion, or which nested scope fields matter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb plus resource (delete memories) and names both selection modes (by id or by query), along with the soft/hard delete distinction. None of the sibling tools (memory_search, memory_add, memory_profile, memory_consolidate...) covers deletion, so an agent can route here without sibling ambiguity, though the description never states that explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the 'soft-delete by default, hard=true physically deletes' framing, which gives a usable default-vs-escalation rule. There is no explicit when-not or caution about irreversible hard deletes, and no named alternative for non-destructive cleanup.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.